search_callsets

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It clearly states the tool retrieves callsets via BrAPI and writes sample_metadata.csv, and it explains the semantic difference between sample_name and callSetName. However, it does not mention whether an existing CSV is overwritten or any failure behavior for empty results, though these are minor for a read-and-dump tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and every subsequent sentence adds value: output format, column semantics, join behavior, and sibling distinction. There is no filler or repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, two well-documented parameters, an existing output schema, and no annotations, the description is complete. It covers what the tool does, what it writes, how the output should be interpreted, and when to choose it over get_germplasm_metadata.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already well documented, especially variant_set_db_id with detailed guidance about copying the exact string. The tool description adds context about the output file and naming semantics but does not materially enrich the meaning of the two parameters themselves beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Dump per-sample (callset) metadata for a run', naming the exact output file and columns. It also explicitly distinguishes itself from get_germplasm_metadata as the 'sample/callset-level counterpart', so an agent can tell siblings apart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives an explicit when-to-use rule: 'use it when the germplasm (accession) level exposes no attributes but the samples do.' It also names the alternative tool directly, and the parameter schema reinforces how to obtain the correct variant_set_db_id.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.